cs.RO · 2026-10-01 · No. 130
Robotics, 2026-10-01.
12 new papers in cs.RO. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
12 entries-
01
DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents
Haoyuan Deng, Jiebin Liu, Tengxiao Zhang, Langning Yan, Hongye Cao, Ziwei Wang
cs.RO · cs.AI · cs.LG
Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system component should be revised. We propose DynaHarness, a dynamic physical harness that couples semantic reasoning with physical...
-
02
STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot Interaction
Nathan Tsoi, Michael J. Munje, Tejas Oberoi, Rishab Maheshwari, Pengen Zheng, Tanush Chauhan, Peter Stone, Joydeep Biswas
cs.RO · cs.LG
Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-Language Models (VLMs) exhibit promising capabilities such as object recognition, common-sense reasoning, and contextual understanding, capabilities that align with the nuanced requirements of social robot navigation. However, it remains unclear whether VLMs can accurately understand complex...
-
03
PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors
Seungeun Rho, Wontaek Kim, Danfei Xu, Sehoon Ha
cs.RO · cs.AI · cs.LG
We present PrefPI (Preference-Guided Policy Iteration), an iterative framework for steering pretrained generative robot policies using only relative preferences over self-generated trajectories. Unlike prior preference-learning methods that primarily sharpen modes already represented by the policy, we study steering beyond the initial effective support, where desired behaviors are rarely or never observed under the initial policy. Our key...
-
04
Tactile Curiosity Drives Robot Interaction
Klemens Iten, Alexander Proshkin, Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, Carmelo Sferrazza
cs.RO · cs.AI
Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampling to discover new strategies, resulting in agents that allocate most of their training budget to motions in free space, away from the contacts from which manipulation skills emerge. Existing intrinsic motivation methods based on model disagreement or epistemic uncertainty improve on...
-
05
BatSLAM 2.0: Sequence-Verified Sonar Place Recognition in a Robust Pose Graph
Jan Steckel
cs.RO · cs.AI · cs.LG · eess.SY
Echolocating bats can navigate dark and cluttered spaces using echolocation. Over a decade ago, BatSLAM showed that a robot with a biomimetic binaural sonar can build a topological map of the environment, by recognizing places from the received acoustic signals. Sonar place recognition, however, is ambiguous by nature: corridors produce nearly identical echo trains, and wrong loop closure can collapse the topological map. In this paper, we...
-
06
When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models
Hung-Jen Chen, Yu-Hsun Hou, Yan-Hong Chen, Yan-Fu Chen, Binghua Cai, Min Sun, Chun-Yi Lee
cs.RO · cs.LG
Vision-language-action (VLA) models can exceed 90% success on in-distribution tasks and withstand nuisance changes that preserve the required action, yet fail under counterfactual changes that demand a different action. Aggregate robustness scores can therefore conceal a more specific failure, in which a policy responds to both language and vision yet does not combine them to select the action the task requires. We call this failure...
-
07
TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks
Yiming Gao, Shaocheng Luo
cs.RO · cs.AI · eess.SY
Physical LiDAR attacks are often evaluated using fixed primitives and manually selected parameters, despite their strong dependence on surrounding traffic. We present TACTIC, a scene-aware framework that uses a multimodal large language model (MLLM) to coordinate state-adaptive roadside LiDAR attacks. Under a gray-box threat model, TACTIC relies only on an attacker-operated roadside perception stack, without accessing the victim LiDAR's...
-
08
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
Mingyue Cui, Zheyuan Liu, Yihan Zhu, Zheyuan Zhang, Meng Jiang
cs.RO · cs.AI
Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments require balancing task success with unintended contact. Runtime shields can correct individual actions, but they leave the underlying policy unchanged, so repeated disagreements may create a persistent policy-shield mismatch that blocks task progress. To address this challenge, we introduce FailBank, a four-stage self-evolving...
-
09
DiffWAM: A Fast and Efficient Navigation World Action Model
Mo Zhu, Yuze Wu, Xijie Huang, Xiao Cui, Fei Gao, Xin Zhou
cs.RO · cs.AI
Pretrained video foundation models encode rich semantic and spatiotemporal priors for embodied navigation, yet converting these priors into UAV motion typically requires expensive future-video synthesis and geometric reconstruction. We investigate whether the motion implicit in future visual prediction can instead be recovered directly from the predictive representations of a frozen video model. To this end, we present DiffWAM, a...
-
10
RoboCoach: World Models as Active Coaches for Compositional Robot Skills
Jiajun Liu, Yifan Chen, Yichao Liu, Jiayi Zhang, Ruoqu Chen, Shaoxuan Xie, Guocai Yao, Mengdi Xu, Sen Cui, Changshui Zhang
cs.RO · cs.AI
Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstrations is costly. A practical self-improving system must decide both what to teach next and where to apply that supervision. We present ROBOCOACH, a world-model-guided coaching framework that uses imagined failures to guide demonstration requests and expert updates. Its Route-Imagine-Diagnose-Improve...
-
11
Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization
Xinhao Yang, Wenhao Wu, Ning Lv, Yanshen Ding, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Zhi Wang
cs.RO · cs.AI
3D visuomotor policies provide a strong foundation for spatially precise manipulation, yet current text-to-3D policies struggle to follow unseen fine-grained behavioral specifications beyond those covered by demonstrations. We study this challenge as unseen specification generalization, where language specifies behaviorally significant variations, such as target position, displacement, or articulated state, that are absent from policy...
-
12
ECHO-G: Embodied Co-speech Humanoid mOtion Generation
Yizhao Li, Pusen Gao, Ming Wang, Shaojie Shen, Shuo Yang, Hao Xu
cs.RO · cs.AI
Generating full-body co-speech motion for humanoid robots requires coordinating speech prosody, linguistic content, and embodiment-specific motion. To this end, we present ECHO-G, a framework jointly conditioned on speech audio and timed transcripts. Its Speech-Grounded Diffusion Transformer (SGDiT) combines frame-aligned acoustic features with token-level linguistic context, preserving their distinct granularities. Trained with rectified...
This edition is part of The Daily Abstract — cs.RO archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.